Research on Flight Accidents Prediction based Back Propagation Neural Network

TL;DR

This paper develops a back-propagation neural network model to predict flight accidents by analyzing historical flight data, aiming to enhance aviation safety through early risk detection.

Contribution

It introduces a neural network-based approach for flight accident prediction using diverse flight-related data, improving prediction accuracy over traditional methods.

Findings

The model achieves high accuracy in accident prediction.

Optimized neural network parameters enhance performance.

The approach demonstrates reliability in safety assessments.

Abstract

With the rapid development of civil aviation and the significant improvement of people's living standards, taking an air plane has become a common and efficient way of travel. However, due to the flight characteris-tics of the aircraft and the sophistication of the fuselage structure, flight de-lays and flight accidents occur from time to time. In addition, the life risk factor brought by aircraft after an accident is also the highest among all means of transportation. In this work, a model based on back-propagation neural network was used to predict flight accidents. By collecting historical flight data, including a variety of factors such as meteorological conditions, aircraft technical condition, and pilot experience, we trained a backpropaga-tion neural network model to identify potential accident risks. In the model design, a multi-layer perceptron structure is used to optimize the network performance by adjusting the number of hidden layer nodes and the learning rate. Experimental analysis shows that the model can effectively predict flight accidents with high accuracy and reliability.